
# import library pandas
import pandas as pd

# Import library numpy
import numpy as np

# Import library matplotlib dan seaborn untuk visualisasi
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

# Import Module LinearRegression digunakan untuk memanggil algoritma Linear Regression.
from sklearn import linear_model

# import Module train_test_split digunakan untuk membagi data kita menjadi training dan testing set.
from sklearn.model_selection import train_test_split

# import modul mean_absolute_error dari library sklearn
from sklearn.metrics import mean_absolute_error

#import math agar program dapat menggunakan semua fungsi yang ada pada modul math.(ex:sqrt)
import math

# me-non aktifkan peringatan pada python
import warnings 
warnings.filterwarnings('ignore')


#Panggil file (load file bernama CarPrice_Assignment.csv) dan simpan dalam dataframe Lalu tampilkan 10 baris awal dataset dengan function head()
data = 'CarPrice_Assignment.csv'
df = pd.read_csv(data)
df.head(10)


# melihat jumlah baris dan jumlah kolom (bentuk data) pada data df dengan fungsi .shape 
df.shape

(205, 26)


# Melihat Informasi lebih detail mengenai struktur DataFrame dapat dilihat menggunakan fungsi info()
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 205 entries, 0 to 204
Data columns (total 26 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   car_ID            205 non-null    int64  
 1   symboling         205 non-null    int64  
 2   CarName           205 non-null    object 
 3   fueltype          205 non-null    object 
 4   aspiration        205 non-null    object 
 5   doornumber        205 non-null    object 
 6   carbody           205 non-null    object 
 7   drivewheel        205 non-null    object 
 8   enginelocation    205 non-null    object 
 9   wheelbase         205 non-null    float64
 10  carlength         205 non-null    float64
 11  carwidth          205 non-null    float64
 12  carheight         205 non-null    float64
 13  curbweight        205 non-null    int64  
 14  enginetype        205 non-null    object 
 15  cylindernumber    205 non-null    object 
 16  enginesize        205 non-null    int64  
 17  fuelsystem        205 non-null    object 
 18  boreratio         205 non-null    float64
 19  stroke            205 non-null    float64
 20  compressionratio  205 non-null    float64
 21  horsepower        205 non-null    int64  
 22  peakrpm           205 non-null    int64  
 23  citympg           205 non-null    int64  
 24  highwaympg        205 non-null    int64  
 25  price             205 non-null    float64
dtypes: float64(8), int64(8), object(10)
memory usage: 41.8+ KB


# melihat statistik data untuk data numeric seperti count, mean, standard deviation, maximum, mininum, dan quartile.
df.describe()


# cek nilai yang hilang / missing values di dalam data
df.isna().sum()

car_ID              0
symboling           0
CarName             0
fueltype            0
aspiration          0
doornumber          0
carbody             0
drivewheel          0
enginelocation      0
wheelbase           0
carlength           0
carwidth            0
carheight           0
curbweight          0
enginetype          0
cylindernumber      0
enginesize          0
fuelsystem          0
boreratio           0
stroke              0
compressionratio    0
horsepower          0
peakrpm             0
citympg             0
highwaympg          0
price               0
dtype: int64


df.corr()


def pp(x,y,z):
    sns.jointplot(df, x_vars=[x,y,z], y_vars='price',size=4, aspect=1, kind='scatter')
    plt.show()

pp('enginesize','boreratio','stroke')
pp('compressionratio','horsepower','peakrpm')
pp('wheelbase','citympg','highwaympg')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
C:\Users\ACERGC~1\AppData\Local\Temp/ipykernel_16772/1582197291.py in <module>
      3     plt.show()
      4 
----> 5 pp('enginesize','boreratio','stroke')
      6 pp('compressionratio','horsepower','peakrpm')
      7 pp('wheelbase','citympg','highwaympg')

C:\Users\ACERGC~1\AppData\Local\Temp/ipykernel_16772/1582197291.py in pp(x, y, z)
      1 def pp(x,y,z):
----> 2     sns.jointplot(df, x_vars=[x,y,z], y_vars='price',size=4, aspect=1, kind='scatter')
      3     plt.show()
      4 
      5 pp('enginesize','boreratio','stroke')

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\_decorators.py in inner_f(*args, **kwargs)
     44             )
     45         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 46         return f(**kwargs)
     47     return inner_f
     48 

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\axisgrid.py in jointplot(x, y, data, kind, color, height, ratio, space, dropna, xlim, ylim, marginal_ticks, joint_kws, marginal_kws, hue, palette, hue_order, hue_norm, **kwargs)
   2228 
   2229     # Initialize the JointGrid object
-> 2230     grid = JointGrid(
   2231         data=data, x=x, y=y, hue=hue,
   2232         palette=palette, hue_order=hue_order, hue_norm=hue_norm,

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\_decorators.py in inner_f(*args, **kwargs)
     44             )
     45         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 46         return f(**kwargs)
     47     return inner_f
     48 

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\axisgrid.py in __init__(self, x, y, data, height, ratio, space, dropna, xlim, ylim, size, marginal_ticks, hue, palette, hue_order, hue_norm)
   1700 
   1701         # Process the input variables
-> 1702         p = VectorPlotter(data=data, variables=dict(x=x, y=y, hue=hue))
   1703         plot_data = p.plot_data.loc[:, p.plot_data.notna().any()]
   1704 

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\_core.py in __init__(self, data, variables)
    603     def __init__(self, data=None, variables={}):
    604 
--> 605         self.assign_variables(data, variables)
    606 
    607         for var, cls in self._semantic_mappings.items():

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\_core.py in assign_variables(self, data, variables)
    666         else:
    667             self.input_format = "long"
--> 668             plot_data, variables = self._assign_variables_longform(
    669                 data, **variables,
    670             )

e:\information system\python project\microcredential2021\lib\site-packages\seaborn\_core.py in _assign_variables_longform(self, data, **kwargs)
    925         # Construct a tidy plot DataFrame. This will convert a number of
    926         # types automatically, aligning on index in case of pandas objects
--> 927         plot_data = pd.DataFrame(plot_data)
    928 
    929         # Reduce the variables dictionary to fields with valid data

e:\information system\python project\microcredential2021\lib\site-packages\pandas\core\frame.py in __init__(self, data, index, columns, dtype, copy)
    612         elif isinstance(data, dict):
    613             # GH#38939 de facto copy defaults to False only in non-dict cases
--> 614             mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
    615         elif isinstance(data, ma.MaskedArray):
    616             import numpy.ma.mrecords as mrecords

e:\information system\python project\microcredential2021\lib\site-packages\pandas\core\internals\construction.py in dict_to_mgr(data, index, columns, dtype, typ, copy)
    462         # TODO: can we get rid of the dt64tz special case above?
    463 
--> 464     return arrays_to_mgr(
    465         arrays, data_names, index, columns, dtype=dtype, typ=typ, consolidate=copy
    466     )

e:\information system\python project\microcredential2021\lib\site-packages\pandas\core\internals\construction.py in arrays_to_mgr(arrays, arr_names, index, columns, dtype, verify_integrity, typ, consolidate)
    117         # figure out the index, if necessary
    118         if index is None:
--> 119             index = _extract_index(arrays)
    120         else:
    121             index = ensure_index(index)

e:\information system\python project\microcredential2021\lib\site-packages\pandas\core\internals\construction.py in _extract_index(data)
    623 
    624         if not indexes and not raw_lengths:
--> 625             raise ValueError("If using all scalar values, you must pass an index")
    626 
    627         if have_series:

ValueError: If using all scalar values, you must pass an index


plt.plot(figsize = (8,8))
data_fitur = df[['enginesize', 'boreratio', 'stroke','compressionratio', 'horsepower', 'peakrpm', 'wheelbase', 'citympg', 'highwaympg']]
sns.heatmap(data_fitur.corr(), annot=False,fmt="f").set_title("Korelasi Heatmap Calon Variabel X")
plt.show()


plt.scatter(df['enginesize'], df['price'])
plt.xlabel('Enginesize')
plt.ylabel('Price')
plt.title('Scatter Plot enginesize vs Price')
plt.show()


# Prepare data
# Pertama, buat variabel x dan y.
x = df['enginesize'].values.reshape(-1,1)
y = df['price'].values.reshape(-1,1)


x_mean = np.mean(df['enginesize'])
y_mean = np.mean(df['price'])
print('nilai mean var x: ', x_mean,'\n'
      'nilai mean var y: ', y_mean)

nilai mean var x:  126.90731707317073 
nilai mean var y:  13276.710570731706


atas = sum((x - x_mean)*(y - y_mean))
bawah = math.sqrt((sum((x - x_mean)**2)) * (sum((y - y_mean)**2)))
correlation = atas/bawah
print('Nilai Correlation Coefficient: ', correlation)

Nilai Correlation Coefficient:  [0.8741448]


# slope
# Slope adalah tingkat kemiringan garis, intercept 
# adalah jarak titik y pada garis dari titik 0
variance = sum((x - x_mean)**2)
covariance = sum((x - x_mean) * (y - y_mean))
theta_1 = covariance/variance
print('Nilai theta_1: ', theta_1)

Nilai theta_1:  [167.69841639]


# intercept
theta_0 = y_mean - (theta_1 * x_mean)
print('Nilai theta_1: ', theta_0)

Nilai theta_1:  [-8005.44553115]


# prediction manual
y_pred = theta_0 + (theta_1 * 130)

print(y_pred)

[13795.34859997]


# visualisasi prediksi dengan scatter plot
y_pred = theta_0 + (theta_1 * x)

plt.scatter(df['enginesize'], df['price'])
plt.plot(x, y_pred, c='r')
plt.xlabel('enginesize')
plt.ylabel('Price')
plt.title('Plot enginesize vs Price')

Text(0.5, 1.0, 'Plot enginesize vs Price')


X_train, X_test, y_train, y_test = train_test_split(x, y, train_size = 0.8, test_size = 0.2, random_state = 100)


regressor = linear_model.LinearRegression()


regressor.fit(X_train, y_train)

LinearRegression()


print(regressor.coef_)
print(regressor.intercept_)

[[168.17363122]]
[-8037.06049611]


regressor.score(X_test, y_test)

0.8068161903454086


print('Correlation: ', math.sqrt(regressor.score(X_test, y_test)))

Correlation:  0.8982294753265496


y_prediksi = regressor.predict(X_test)

plt.scatter(df['enginesize'], df['price'])
plt.plot(X_test, y_prediksi, c='r')
plt.xlabel('enginesize')
plt.ylabel('Price')
plt.title('Plot enginesize vs Price')

Text(0.5, 1.0, 'Plot enginesize vs Price')


#Prediksi harga mobil dengan enginesize 130.

print('nilai prediksi harga dengan enginesize 100 : ', regressor.predict([[100]]))
print('nilai prediksi harga dengan enginesize 150 : ', regressor.predict([[150]]))
print('nilai prediksi harga dengan enginesize 200 : ', regressor.predict([[200]]))

nilai prediksi harga dengan enginesize 100 :  [[8780.30262568]]
nilai prediksi harga dengan enginesize 150 :  [[17188.98418658]]
nilai prediksi harga dengan enginesize 200 :  [[25597.66574748]]


np_table = np.concatenate((X_test,y_test,y_prediksi), axis=1)
new_dataframe = pd.DataFrame(data=np_table, columns=['x_test','y_test','y_predict'])


new_dataframe


from sklearn import metrics  
print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, y_prediksi))  
print('Mean Squared Error:', metrics.mean_squared_error(y_test, y_prediksi))  
print('Root Mean Squared Error:', np.sqrt(metrics.mean_absolute_error(y_test, y_prediksi)))

Mean Absolute Error: 3123.611515387693
Mean Squared Error: 14882644.972928163
Root Mean Squared Error: 55.88927907378743


plt.title('Comparison of Y values in test and the Predicted values')
plt.ylabel('Test Set')
plt.xlabel('Predicted values')
plt.plot(y_test, '.', y_prediksi, 'x')
plt.show

<function matplotlib.pyplot.show(close=None, block=None)>

	car_ID	symboling	CarName	fueltype	aspiration	doornumber	carbody	drivewheel	enginelocation	wheelbase	...	enginesize	fuelsystem	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
0	1	3	alfa-romero giulia	gas	std	two	convertible	rwd	front	88.6	...	130	mpfi	3.47	2.68	9.0	111	5000	21	27	13495.000
1	2	3	alfa-romero stelvio	gas	std	two	convertible	rwd	front	88.6	...	130	mpfi	3.47	2.68	9.0	111	5000	21	27	16500.000
2	3	1	alfa-romero Quadrifoglio	gas	std	two	hatchback	rwd	front	94.5	...	152	mpfi	2.68	3.47	9.0	154	5000	19	26	16500.000
3	4	2	audi 100 ls	gas	std	four	sedan	fwd	front	99.8	...	109	mpfi	3.19	3.40	10.0	102	5500	24	30	13950.000
4	5	2	audi 100ls	gas	std	four	sedan	4wd	front	99.4	...	136	mpfi	3.19	3.40	8.0	115	5500	18	22	17450.000
5	6	2	audi fox	gas	std	two	sedan	fwd	front	99.8	...	136	mpfi	3.19	3.40	8.5	110	5500	19	25	15250.000
6	7	1	audi 100ls	gas	std	four	sedan	fwd	front	105.8	...	136	mpfi	3.19	3.40	8.5	110	5500	19	25	17710.000
7	8	1	audi 5000	gas	std	four	wagon	fwd	front	105.8	...	136	mpfi	3.19	3.40	8.5	110	5500	19	25	18920.000
8	9	1	audi 4000	gas	turbo	four	sedan	fwd	front	105.8	...	131	mpfi	3.13	3.40	8.3	140	5500	17	20	23875.000
9	10	0	audi 5000s (diesel)	gas	turbo	two	hatchback	4wd	front	99.5	...	131	mpfi	3.13	3.40	7.0	160	5500	16	22	17859.167

	car_ID	symboling	wheelbase	carlength	carwidth	carheight	curbweight	enginesize	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
count	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000	205.000000
mean	103.000000	0.834146	98.756585	174.049268	65.907805	53.724878	2555.565854	126.907317	3.329756	3.255415	10.142537	104.117073	5125.121951	25.219512	30.751220	13276.710571
std	59.322565	1.245307	6.021776	12.337289	2.145204	2.443522	520.680204	41.642693	0.270844	0.313597	3.972040	39.544167	476.985643	6.542142	6.886443	7988.852332
min	1.000000	-2.000000	86.600000	141.100000	60.300000	47.800000	1488.000000	61.000000	2.540000	2.070000	7.000000	48.000000	4150.000000	13.000000	16.000000	5118.000000
25%	52.000000	0.000000	94.500000	166.300000	64.100000	52.000000	2145.000000	97.000000	3.150000	3.110000	8.600000	70.000000	4800.000000	19.000000	25.000000	7788.000000
50%	103.000000	1.000000	97.000000	173.200000	65.500000	54.100000	2414.000000	120.000000	3.310000	3.290000	9.000000	95.000000	5200.000000	24.000000	30.000000	10295.000000
75%	154.000000	2.000000	102.400000	183.100000	66.900000	55.500000	2935.000000	141.000000	3.580000	3.410000	9.400000	116.000000	5500.000000	30.000000	34.000000	16503.000000
max	205.000000	3.000000	120.900000	208.100000	72.300000	59.800000	4066.000000	326.000000	3.940000	4.170000	23.000000	288.000000	6600.000000	49.000000	54.000000	45400.000000

	car_ID	symboling	wheelbase	carlength	carwidth	carheight	curbweight	enginesize	boreratio	stroke	compressionratio	horsepower	peakrpm	citympg	highwaympg	price
car_ID	1.000000	-0.151621	0.129729	0.170636	0.052387	0.255960	0.071962	-0.033930	0.260064	-0.160824	0.150276	-0.015006	-0.203789	0.015940	0.011255	-0.109093
symboling	-0.151621	1.000000	-0.531954	-0.357612	-0.232919	-0.541038	-0.227691	-0.105790	-0.130051	-0.008735	-0.178515	0.070873	0.273606	-0.035823	0.034606	-0.079978
wheelbase	0.129729	-0.531954	1.000000	0.874587	0.795144	0.589435	0.776386	0.569329	0.488750	0.160959	0.249786	0.353294	-0.360469	-0.470414	-0.544082	0.577816
carlength	0.170636	-0.357612	0.874587	1.000000	0.841118	0.491029	0.877728	0.683360	0.606454	0.129533	0.158414	0.552623	-0.287242	-0.670909	-0.704662	0.682920
carwidth	0.052387	-0.232919	0.795144	0.841118	1.000000	0.279210	0.867032	0.735433	0.559150	0.182942	0.181129	0.640732	-0.220012	-0.642704	-0.677218	0.759325
carheight	0.255960	-0.541038	0.589435	0.491029	0.279210	1.000000	0.295572	0.067149	0.171071	-0.055307	0.261214	-0.108802	-0.320411	-0.048640	-0.107358	0.119336
curbweight	0.071962	-0.227691	0.776386	0.877728	0.867032	0.295572	1.000000	0.850594	0.648480	0.168790	0.151362	0.750739	-0.266243	-0.757414	-0.797465	0.835305
enginesize	-0.033930	-0.105790	0.569329	0.683360	0.735433	0.067149	0.850594	1.000000	0.583774	0.203129	0.028971	0.809769	-0.244660	-0.653658	-0.677470	0.874145
boreratio	0.260064	-0.130051	0.488750	0.606454	0.559150	0.171071	0.648480	0.583774	1.000000	-0.055909	0.005197	0.573677	-0.254976	-0.584532	-0.587012	0.553173
stroke	-0.160824	-0.008735	0.160959	0.129533	0.182942	-0.055307	0.168790	0.203129	-0.055909	1.000000	0.186110	0.080940	-0.067964	-0.042145	-0.043931	0.079443
compressionratio	0.150276	-0.178515	0.249786	0.158414	0.181129	0.261214	0.151362	0.028971	0.005197	0.186110	1.000000	-0.204326	-0.435741	0.324701	0.265201	0.067984
horsepower	-0.015006	0.070873	0.353294	0.552623	0.640732	-0.108802	0.750739	0.809769	0.573677	0.080940	-0.204326	1.000000	0.131073	-0.801456	-0.770544	0.808139
peakrpm	-0.203789	0.273606	-0.360469	-0.287242	-0.220012	-0.320411	-0.266243	-0.244660	-0.254976	-0.067964	-0.435741	0.131073	1.000000	-0.113544	-0.054275	-0.085267
citympg	0.015940	-0.035823	-0.470414	-0.670909	-0.642704	-0.048640	-0.757414	-0.653658	-0.584532	-0.042145	0.324701	-0.801456	-0.113544	1.000000	0.971337	-0.685751
highwaympg	0.011255	0.034606	-0.544082	-0.704662	-0.677218	-0.107358	-0.797465	-0.677470	-0.587012	-0.043931	0.265201	-0.770544	-0.054275	0.971337	1.000000	-0.697599
price	-0.109093	-0.079978	0.577816	0.682920	0.759325	0.119336	0.835305	0.874145	0.553173	0.079443	0.067984	0.808139	-0.085267	-0.685751	-0.697599	1.000000

	x_test	y_test	y_predict
0	98.0	7738.0	8443.955363
1	109.0	8495.0	10293.865307
2	122.0	8845.0	12480.122512
3	98.0	9298.0	8443.955363
4	108.0	7603.0	10125.691675
5	122.0	11245.0	12480.122512
6	130.0	18420.0	13825.511562
7	140.0	16503.0	15507.247874
8	146.0	17669.0	16516.289662
9	181.0	17199.0	22402.366754
10	141.0	16845.0	15675.421506
11	121.0	18150.0	12311.948881
12	120.0	15580.0	12143.775250
13	110.0	12945.0	10462.038938
14	308.0	40960.0	43760.417919
15	92.0	6855.0	7434.913576
16	98.0	6938.0	8443.955363
17	121.0	12170.0	12311.948881
18	140.0	18280.0	15507.247874
19	156.0	14869.0	18198.025974
20	141.0	13415.0	15675.421506
21	141.0	16515.0	15675.421506
22	194.0	32528.0	24588.623960
23	90.0	5572.0	7098.566314
24	146.0	8449.0	16516.289662
25	181.0	13499.0	22402.366754
26	156.0	12764.0	18198.025974
27	183.0	28176.0	22738.714017
28	108.0	16925.0	10125.691675
29	119.0	11048.0	11975.601619
30	92.0	6189.0	7434.913576
31	209.0	30760.0	27111.228428
32	152.0	13860.0	17525.331449
33	141.0	19045.0	15675.421506
34	120.0	16630.0	12143.775250
35	110.0	10698.0	10462.038938
36	121.0	15040.0	12311.948881
37	146.0	9989.0	16516.289662
38	97.0	6849.0	8275.781732
39	122.0	8948.0	12480.122512
40	304.0	45400.0	43087.723394

Hands-On¶

Tugas Mandiri Pertemuan 10¶

Latihan (1)¶

Melakukan import library yang dibutuhkan¶

Load Dataset¶

Latihan (2)¶

Review Dataset¶

Visualisasi data untuk pemilihan fitur / variabel independen X¶

Latihan (3)¶

untuk dapat menentukan lebih detail / akurat dalam pemilihan fitur dapat dilihat dari hubungan korelasi nya dengan function corr()¶

Latihan (4)¶

Buat Visualisasi scater plot dari kolom:¶

Latihan (5)¶

Buat Visualisasi Heatmap dari kolom:¶

Latihan (6)¶

Buat Visualisasi Scatter Plot antara calon variabel X(enginesize) dan y(price):¶

Latihan (7)¶

definisi variabel X(enginesize) dan y(price):¶

Latihan (8)¶

definisi variabel nilai mean/rata-rata X(enginesize) dan nilai mean/rata-rata y(price):¶

Latihan (9)¶

carilah nilai koefisien korelasi nya dengan rumus dibawah:¶

carilah nilai parameter theta 1 dan theta 0 dengan rumus dibawah:¶

Latihan (10)¶

carilah nilai theta_1 atau nilai slope¶

Latihan (11)¶

carilah nilai theta_0 atau nilai intercept¶

Maka persamaan garis :¶

y = 167.69x - 8005.44¶

Latihan (12)¶

carilah nilai prediksi secara manual dan buatlah visualisasi scater plot nya¶

Linier Regression dengan menggunakan library sklearn¶

Latihan (13)¶

split data train dan test dengan function train_test_split() dengan train_size=0.8, test_size=0.2 dan random_state=100¶

Latihan (14)¶

buat object variabel linier regression¶

Latihan (15)¶

training the model menggunakan training data yang sudah displit sebelumnya.¶

Latihan (16)¶

cari tau nilai slope/koefisien (m) dan intercept (b), dengan menggunakan function dari library sklearn -> LinierRegression¶

y = 168.17x - 8037.06¶

Latihan (17)¶

cari tahu accuracy score dari model kita menggunakan testing data yang sudah displit sebelumnya. Dan nilai korelasinya¶

Latihan (18)¶

visualisasi Regression Line menggunakan data testing.¶

Latihan (19)¶

Setelah kita yakin dengan model yang dibuat, selanjutnya adalah prediksi dari harga mobil dengan enginesize 100, 150, dan 200.¶

Latihan (20)¶

Cetak nilai Mean Absolute Error, Mean Squared Error, dan Root Mean Squared Error¶